Hugging Face's logo

xMaulana
/
FinMatcha-3B-Instruct

Text Generation
Safetensors
Indonesian
llama
Indonesian
Chat
Instruct
conversational
Eval Results
Model card Files Community
7
FinMatcha-3B-Instruct / README.md
xMaulana's picture
xMaulana
Update README.md
242b4e9 verified
preview code
|
raw
history blame
2.86 kB
metadata
license: apache-2.0
tags:
  - Indonesian
  - Chat
  - Instruct
language:
  - id
  - en
base_model:
  - meta-llama/Llama-3.2-3B-Instruct
datasets:
  - NekoFi/alpaca-gpt4-indonesia-cleaned
pipeline_tag: text-generation

image/jpeg

Finmatcha-3B

Finmatcha is a powerful Indonesian-focused large language model (LLM) fine-tuned using the Llama-3.2-3B-Instruct base model. The model has been trained to handle a variety of natural language processing tasks such as text generation, summarization, translation, and question-answering, with a special emphasis on understanding and generating Indonesian text.

This model has been fine-tuned on a wide array of Indonesian datasets, making it adept at handling the nuances of the Indonesian language, from formal to colloquial speech. It also supports English for bilingual applications.

Model Details

How to use

Installation

To use the Finmatcha model, install the required dependencies:

pip install transformers>=4.45

Usage 

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "xMaulana/FinMatcha-3B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

inputs = tokenizer("berikan aku resep nasi goreng super lezat", return_tensors="pt").to("cuda")
outputs = model.generate(inputs.input_ids, 
                          max_new_tokens = 1024,
                          pad_token_id=tokenizer.pad_token_id,
                          eos_token_id=tokenizer.eos_token_id,
                          temperature=0.7,
                          do_sample=True, 
                          top_k=5, 
                          top_p=0.9,
                          repetition_penalty=1.1
                         )
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Limitations

  • The model is primarily focused on the Indonesian language and may not perform as well on non-Indonesian tasks.
  • As with all LLMs, cultural and contextual biases can be present.

License

The model is licensed under the Apache-2.0.

Contributing

We welcome contributions to enhance and improve Finmatcha. Feel free to open issues or submit pull requests for improvements.